© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7469
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to sports tournaments, especially basketball

    oai_token-act-pair · gemini-2.0-flash

    sports and competition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pexpr
    -0.49
    رای
    -0.49
     "..\..\..\
    -0.47
    bio
    -0.46
    adget
    -0.44
    Biographies
    -0.43
    PHEN
    -0.43
    atta
    -0.40
     bio
    -0.40
     scel
    -0.40
    POSITIVE LOGITS
    HtmlAttribute
    0.65
    __':
    0.62
     whoſe
    0.62
     snippetHide
    0.61
    OGND
    0.60
    mybatisplus
    0.59
    لينكات
    0.58
     Drapeau
    0.56
     pageContext
    0.55
    riebenen
    0.55
    Activations Density 0.608%

    No Known Activations